V0.32

v0.32 release notes:

New features:

• Off Threshold: Introduced a new feature to customise the off threshold for automatically ending the listening session.
• Gesture-Audio Player Active Stats Save: Added the ability to save active statistics for the gesture-audio player.
• PRiSM_MGR_Performers: Introduced a new interface for performance that supports the use of up to 12 models simultaneously. Each model channel has modules for independent Setting, Prediction, OSC IO, MIDI, and Gesture-audio player. More details will be added to the README soon.

Bug Fixes

• Resolved issues related to saving and loading model.
• Fixed a user interface issue affecting the spectrum components settings
• Enhanced the gesture-audio player's stability and functionality.

Full Changelog: v0.3...v0.32

v0.3

v0.3 release notes:

New features:

• Multiple Input Channels Support: Now supporting up to 8 channels for diverse audio setup configurations.
• Data Augmentation: Introducing data augmentation techniques for more robust gesture recognition. This includes applying pitch shift and time stretching to enhance the training set using existing data.
• Prediction Accuracy Threshold: Introducing the prediction accuracy threshold setting which can filter predicted results below a certain accuracy threshold.
• Spectrum Components Settings: Users can now modify the number of frequency components in the spectrogram, allowing for more detailed feature extraction and potentially improving model accuracy.
• OSC Receive Capability: Includes the ability to receive OSC messages to control some parameters on the fly. The receive port is 1123
• Validation Module: The new validation module enables users to test the accuracy of their trained models using saved samples and provides metrics such as gesture-specific accuracy and average accuracy.
• Gesture-Audio Mapping Playback: Enhanced interaction with the ability to map recognised gestures to specific audio playback.
• Machine Learning Model Improvements: Improved the training process of the ML model based on custom gesture recordings and settings.
• Customisable MIDI Channel: Users can now customise the MIDI output channel.
• User Interface Enhancements: The main interface has been refined for better user experience and accessibility.

Bug Fixes

• Various bug fixes and performance improvements.

Full Changelog: v0.25...v0.3

v0.26b

v0.26b release notes:

New features:

• Drag&drop area in the playback section: drag and drop the new audio file to test.

• Timer in the setting window used to force prediction: The timer will be enabled if it's set to less than the default duration; and disabled when it is more than 6 seconds.

• Input signal meter.

• Gesture audio player: a new section for mapping gestures to audio files. click the 'Audio' button to enable and open the player window.

Bugs fixed:

• Fixed save gesture recording will replace the old file.
• Some improvements for the analysis part.

v0.25b

v0.25b release notes:

• Bugs fixed.
• Save the OSC setting with configurations.
• Merge the configurations and trained model into a single file.

v0.25

v0.25 release notes:

• Bugs fixed
• Reversed the "Play" button labelling.
• Added the input amplitude detector to automatically start recording samples.

Release credits:

• Thanks @davidderoure suggestions

v0.24a

This is a beta release and may contain bugs. Use with caution and at your own risk.